Dual-orthogonal radial basis function networks for nonlinear time series prediction

A new structure of Radial Basis Function (RBF) neural network called the Dual-orthogonal RBF Network (DRBF) is introduced for nonlinear time series prediction. The hidden nodes of a conventional RBF network compare the Euclidean distance between the network input vector and the centres, and the node responses are radially symmetrical. But in time series prediction where the system input vectors are lagged system outputs, which are usually highly correlated, the Euclidean distance measure may not be appropriate. The DRBF network modifies the distance metric by introducing a classification function which is based on the estimation data set. Training the DRBF networks consists of two stages. Learning the classification related basis functions and the important input nodes, followed by selecting the regressors and learning the weights of the hidden nodes. In both cases, a forward Orthogonal Least Squares (OLS) selection procedure is applied, initially to select the important input nodes and then to select the important centres. Simulation results of single-step and multi-step ahead predictions over a test data set are included to demonstrate the effectiveness of the new approach.

On combination of SMOTE and particle swarm optimization based radial basis function classifier for imbalanced problems

The combination of the synthetic minority oversampling technique (SMOTE) and the radial basis function (RBF) classifier is proposed to deal with classification for imbalanced two-class data. In order to enhance the significance of the small and specific region belonging to the positive class in the decision region, the SMOTE is applied to generate synthetic instances for the positive class to balance the training data set. Based on the over-sampled training data, the RBF classifier is constructed by applying the orthogonal forward selection procedure, in which the classifier structure and the parameters of RBF kernels are determined using a particle swarm optimization algorithm based on the criterion of minimizing the leave-one-out misclassification rate. The experimental results on both simulated and real imbalanced data sets are presented to demonstrate the effectiveness of our proposed algorithm.

Sector, region or function? A MAD reassessment of real estate diversification in Great Britain

This paper re-examines whether it is more advantageous in terms of risk reduction to diversify by sector or region by comparing the performance of the ‘conventional’ regional classification of the UK with one based on modern socio-economic criteria using a much larger real estate data set than any previous study and the MAD portfolio approach. The general conclusion of this analysis is that property market sectors still dominate regions, however defined and so should be the first level of analysis when developing a portfolio diversification strategy. This is in line with previous research. When the performance of Functional groups is compared with the ‘conventional’ administrative regions the results here show that, when functionally based, groupings can in some cases provide greater risk reduction. In addition the underlying characteristics of these functional groups may be much more insightful and acceptable to real estate portfolio managers in considering the assets that a portfolio might contain.

Parkinson’s Disease tremor classification – a comparison between Support Vector Machines and neural networks

Deep Brain Stimulation has been used in the study of and for treating Parkinson’s Disease (PD) tremor symptoms since the 1980s. In the research reported here we have carried out a comparative analysis to classify tremor onset based on intraoperative microelectrode recordings of a PD patient’s brain Local Field Potential (LFP) signals. In particular, we compared the performance of a Support Vector Machine (SVM) with two well known artificial neural network classifiers, namely a Multiple Layer Perceptron (MLP) and a Radial Basis Function Network (RBN). The results show that in this study, using specifically PD data, the SVM provided an overall better classification rate achieving an accuracy of 81% recognition.

An effective approach for land-cover classification from airborne lidar fused with co-registered data

Airborne lidar provides accurate height information of objects on the earth and has been recognized as a reliable and accurate surveying tool in many applications. In particular, lidar data offer vital and significant features for urban land-cover classification, which is an important task in urban land-use studies. In this article, we present an effective approach in which lidar data fused with its co-registered images (i.e. aerial colour images containing red, green and blue (RGB) bands and near-infrared (NIR) images) and other derived features are used effectively for accurate urban land-cover classification. The proposed approach begins with an initial classification performed by the Dempster–Shafer theory of evidence with a specifically designed basic probability assignment function. It outputs two results, i.e. the initial classification and pseudo-training samples, which are selected automatically according to the combined probability masses. Second, a support vector machine (SVM)-based probability estimator is adopted to compute the class conditional probability (CCP) for each pixel from the pseudo-training samples. Finally, a Markov random field (MRF) model is established to combine spatial contextual information into the classification. In this stage, the initial classification result and the CCP are exploited. An efficient belief propagation (EBP) algorithm is developed to search for the global minimum-energy solution for the maximum a posteriori (MAP)-MRF framework in which three techniques are developed to speed up the standard belief propagation (BP) algorithm. Lidar and its co-registered data acquired by Toposys Falcon II are used in performance tests. The experimental results prove that fusing the height data and optical images is particularly suited for urban land-cover classification. There is no training sample needed in the proposed approach, and the computational cost is relatively low. An average classification accuracy of 93.63% is achieved.

A unified neurofuzzy model for classification

This work proposes a unified neurofuzzy modelling scheme. To begin with, the initial fuzzy base construction method is based on fuzzy clustering utilising a Gaussian mixture model (GMM) combined with the analysis of covariance (ANOVA) decomposition in order to obtain more compact univariate and bivariate membership functions over the subspaces of the input features. The mean and covariance of the Gaussian membership functions are found by the expectation maximisation (EM) algorithm with the merit of revealing the underlying density distribution of system inputs. The resultant set of membership functions forms the basis of the generalised fuzzy model (GFM) inference engine. The model structure and parameters of this neurofuzzy model are identified via the supervised subspace orthogonal least square (OLS) learning. Finally, instead of providing deterministic class label as model output by convention, a logistic regression model is applied to present the classifier’s output, in which the sigmoid type of logistic transfer function scales the outputs of the neurofuzzy model to the class probability. Experimental validation results are presented to demonstrate the effectiveness of the proposed neurofuzzy modelling scheme.

Language and thought in bilinguals: the case of grammatical number and nonverbal classification preferences

Recent research shows that speakers of languages with obligatory plural marking (English) preferentially categorize objects based on common shape, whereas speakers of nonplural-marking classifier languages (Yucatec and Japanese) preferentially categorize objects based on common material. The current study extends that investigation to the domain of bilingualism. Japanese and English monolinguals, and Japanese–English bilinguals were asked to match novel objects based on either common shape or color. Results showed that English monolinguals selected shape significantly more than Japanese monolinguals, whereas the bilinguals shifted their cognitive preferences as a function of their second language proficiency. The implications of these findings for conceptual representation and cognitive processing in bilinguals are discussed.

Ecophysiological and bioclimatic foundations for a global plant functional classification

Question: What plant properties might define plant functional types (PFTs) for the analysis of global vegetation responses to climate change, and what aspects of the physical environment might be expected to predict the distributions of PFTs? Methods: We review principles to explain the distribution of key plant traits as a function of bioclimatic variables. We focus on those whole-plant and leaf traits that are commonly used to define biomes and PFTs in global maps and models. Results: Raunkiær's plant life forms (underlying most later classifications) describe different adaptive strategies for surviving low temperature or drought, while satisfying requirements for reproduction and growth. Simple conceptual models and published observations are used to quantify the adaptive significance of leaf size for temperature regulation, leaf consistency for maintaining transpiration under drought, and phenology for the optimization of annual carbon balance. A new compilation of experimental data supports the functional definition of tropical, warm-temperate, temperate and boreal phanerophytes based on mechanisms for withstanding low temperature extremes. Chilling requirements are less well quantified, but are a necessary adjunct to cold tolerance. Functional traits generally confer both advantages and restrictions; the existence of trade-offs contributes to the diversity of plants along bioclimatic gradients. Conclusions: Quantitative analysis of plant trait distributions against bioclimatic variables is becoming possible; this opens up new opportunities for PFT classification. A PFT classification based on bioclimatic responses will need to be enhanced by information on traits related to competition, successional dynamics and disturbance.

A radial basis function network classifier to maximise leave-one-out mutual information

tWe develop an orthogonal forward selection (OFS) approach to construct radial basis function (RBF)network classifiers for two-class problems. Our approach integrates several concepts in probabilisticmodelling, including cross validation, mutual information and Bayesian hyperparameter fitting. At eachstage of the OFS procedure, one model term is selected by maximising the leave-one-out mutual infor-mation (LOOMI) between the classifier’s predicted class labels and the true class labels. We derive theformula of LOOMI within the OFS framework so that the LOOMI can be evaluated efficiently for modelterm selection. Furthermore, a Bayesian procedure of hyperparameter fitting is also integrated into theeach stage of the OFS to infer the l2-norm based local regularisation parameter from the data. Since eachforward stage is effectively fitting of a one-variable model, this task is very fast. The classifier construc-tion procedure is automatically terminated without the need of using additional stopping criterion toyield very sparse RBF classifiers with excellent classification generalisation performance, which is par-ticular useful for the noisy data sets with highly overlapping class distribution. A number of benchmarkexamples are employed to demonstrate the effectiveness of our proposed approach.

Novel single trial movement classification based on temporal dynamics of EEG

Various complex oscillatory processes are involved in the generation of the motor command. The temporal dynamics of these processes were studied for movement detection from single trial electroencephalogram (EEG). Autocorrelation analysis was performed on the EEG signals to find robust markers of movement detection. The evolution of the autocorrelation function was characterised via the relaxation time of the autocorrelation by exponential curve fitting. It was observed that the decay constant of the exponential curve increased during movement, indicating that the autocorrelation function decays slowly during motor execution. Significant differences were observed between movement and no moment tasks. Additionally, a linear discriminant analysis (LDA) classifier was used to identify movement trials with a peak accuracy of 74%.

On the application of optimal wavelet filter banks for ECG signal classification

This paper discusses ECG signal classification after parametrizing the ECG waveforms in the wavelet domain. Signal decomposition using perfect reconstruction quadrature mirror filter banks can provide a very parsimonious representation of ECG signals. In the current work, the filter parameters are adjusted by a numerical optimization algorithm in order to minimize a cost function associated to the filter cut-off sharpness. The goal consists of achieving a better compromise between frequency selectivity and time resolution at each decomposition level than standard orthogonal filter banks such as those of the Daubechies and Coiflet families. Our aim is to optimally decompose the signals in the wavelet domain so that they can be subsequently used as inputs for training to a neural network classifier.

Chemical profile of rums as a function of their origin. The use of chemometric techniques for their identification

To identify chemical descriptors to distinguish Cuban from non-Cuban rums, analyses of 44 samples of rum from 15 different countries are described. To provide the chemical descriptors, analyses of the the mineral fraction, phenolic compounds, caramel, alcohols, acetic acid, ethyl acetate, ketones, and aldehydes were carried out. The analytical data were treated through the following chemometric methods: principal component analysis (PCA), partial least square-discriminate analysis (PLS-DA), and linear discriminate analysis (LDA). These analyses indicated 23 analytes as relevant chemical descriptors for the separation of rums into two distinct groups. The possibility of clustering the rum samples investigated through PCA analysis led to an accumulative percentage of 70.4% in the first three principal components, and isoamyl alcohol, n-propyl alcohol, copper, iron, 2-furfuraldehyde (furfuraldehyde), phenylmethanal (benzaldehyde), epicatechin, and vanillin were used as chemical descriptors. By applying the PLS-DA technique to the whole set of analytical data, the following analytes have been selected as descriptors: acetone, sec-butyl alcohol, isobutyl alcohol, ethyl acetate, methanol, isoamyl alcohol, magnesium, sodium, lead, iron, manganese, copper, zinc, 4-hydroxy3,5-dimethoxybenzaldehyde (syringaldehyde), methaldehyde (formaldehyde), 5-hydroxymethyl-2furfuraldehyde (5-HMF), acetalclehyde, 2-furfuraldehyde, 2-butenal (crotonaldehyde), n-pentanal (valeraldehyde), iso-pentanal (isovaleraldehyde), benzaldehyde, 2,3-butanodione monoxime, acetylacetone, epicatechin, and vanillin. By applying the LIDA technique, a model was developed, and the following analytes were selected as descriptors: ethyl acetate, sec-butyl alcohol, n-propyl alcohol, n-butyl alcohol, isoamyl alcohol, isobutyl alcohol, caramel, catechin, vanillin, epicatechin, manganese, acetalclehyde, 4-hydroxy-3-methoxybenzoic acid, 2-butenal, 4-hydroxy-3,5-dimethoxybenzoic acid, cyclopentanone, acetone, lead, zinc, calcium, barium, strontium, and sodium. This model allowed the discrimination of Cuban rums from the others with 88.2% accuracy.

Classification of Boal, Malvazia, Sercial and Verdelho wines based on terpenoid patterns

Thirty-six Madeira wine samples from Boal, Malvazia, Sercial and Verdelho white grape varieties were analyzed in order to estimate the free fraction of monoterpenols and C13 norisoprenoids (terpenoid compounds) using dynamic headspace solid phase micro-extraction (HS-SPME) technique coupled with gas chromatography–mass spectrometry (GC–MS). The average values from three vintages (1998–2000) show that these wines have characteristic profiles of terpenoid compounds. Malvazia wines exhibits the highest values of total free monoterpenols, contrary to Verdelho wines which had the lowest levels of terpenoids but produced the highest concentration of farnesol. The use of multivariate analysis techniques allows establishing relations between the compounds and the varieties under investigation. Principal component analysis (PCA) and linear discriminant analysis (LDA) were applied to the obtained matrix data. A good separation and classification power between the four groups as a function of their varietal origin was observed.

Postoperative renal function evaluation, through RIFLE criteria, of elderly patients who underwent femur fracture surgery under spinal anesthesia

Introduction. The postoperative acute renal failure (ARF) incidence in different kinds of surgery has rarely been studied. Age, cardiac dysfunction, previous renal dysfunction, intraoperative hypoperfusion, and use of nephrotoxic medications are mentioned as risk factors for ARF at the postoperative period. The postoperative ARF definition was based on the creatinine increase by the RIFLE classification (R = risk, I = injury, F = failure, L = loss, E = end stage), which corresponds to a 1.5 creatinine increase, two to three times, respectively, above the basal value. This study aimed to evaluate the postoperative ARF incidence in elderly patients who underwent femur fracture surgery under subarachnoid anesthesia and stratify it by the RIFLE criteria. Methods. Ninety patients older than 65 years under spinal anesthesia with fixed dosage of 15 mg of 0.5% isobaric bupivacaine associated with morphine 50 g were studied. Immediate postoperative creatinine was considered basal and compared with maximal creatinine evaluated at 24, 48, and 72 postoperative hours. Results. The mean age of the patients was 80.27 years. ARF incidence was 24.44% and stratified this way: R = 21.11% and I = 3.33%. Conclusions. In conclusion, the postoperative ARF incidence after femur fracture surgery in patients over 65 years was 24.44%. By analyzing the stratification based on the RIFLE classification, the incidence was categorized as Risk (R) = 21.11% and Injury (I) = 3.33%.

Relationship between global structural parameters and Enzyme Commission hierarchy: Implications for function prediction

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)